ResearchTasksLong-term preference alignmentLong-term preference alignmentFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedStyleDrive (OOD)DMW83Alignment Score (D3)2Mar 27, 2026StyleDrive (ID)DMW92Alignment Score (D1)2Mar 27, 2026